Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4736
    Prev
    Next
    INDEX
    Explanations

    names or words related to nomads

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "nomadic" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FactoryReloaded
    -0.74
     Hebdo
    -0.71
    ++++
    -0.69
    NEY
    -0.68
     Breach
    -0.64
    EVA
    -0.64
    ween
    -0.64
     guiActiveUnfocused
    -0.64
    GER
    -0.62
    ++++++++++++++++
    -0.62
    POSITIVE LOGITS
    inates
    1.09
    nom
    1.04
     Nom
    1.03
    adic
    1.02
     nom
    0.98
    inational
    0.95
    essage
    0.94
    inally
    0.94
    oda
    0.94
    atis
    0.88
    Activations Density 0.024%

    No Known Activations